A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations
Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …
massive model sizes that require significant computational and storage resources. To …
Filter pruning via geometric median for deep convolutional neural networks acceleration
Previous works utilized" smaller-norm-less-important" criterion to prune filters with smaller
norm values in a convolutional neural network. In this paper, we analyze this norm-based …
norm values in a convolutional neural network. In this paper, we analyze this norm-based …
Survey: Exploiting data redundancy for optimization of deep learning
Data redundancy is ubiquitous in the inputs and intermediate results of Deep Neural
Networks (DNN). It offers many significant opportunities for improving DNN performance and …
Networks (DNN). It offers many significant opportunities for improving DNN performance and …
Learning filter pruning criteria for deep convolutional neural networks acceleration
Filter pruning has been widely applied to neural network compression and acceleration.
Existing methods usually utilize pre-defined pruning criteria, such as Lp-norm, to prune …
Existing methods usually utilize pre-defined pruning criteria, such as Lp-norm, to prune …
A good student is cooperative and reliable: CNN-transformer collaborative learning for semantic segmentation
In this paper, we strive to answer the question'how to collaboratively learn convolutional
neural network (CNN)-based and vision transformer (ViT)-based models by selecting and …
neural network (CNN)-based and vision transformer (ViT)-based models by selecting and …
Protopshare: Prototypical parts sharing for similarity discovery in interpretable image classification
In this work, we introduce an extension to ProtoPNet called ProtoPShare which shares
prototypical parts between classes. To obtain prototype sharing we prune prototypical parts …
prototypical parts between classes. To obtain prototype sharing we prune prototypical parts …
Deep ensemble learning for human activity recognition using wearable sensors via filter activation
During the past decade, human activity recognition (HAR) using wearable sensors has
become a new research hot spot due to its extensive use in various application domains …
become a new research hot spot due to its extensive use in various application domains …
Leveraging filter correlations for deep model compression
We present a filter correlation based model compression approach for deep convolutional
neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise …
neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise …
Manipulating identical filter redundancy for efficient pruning on deep and complicated cnn
The existence of redundancy in convolutional neural networks (CNNs) enables us to remove
some filters/channels with acceptable performance drops. However, the training objective of …
some filters/channels with acceptable performance drops. However, the training objective of …
Deep neural network pruning method based on sensitive layers and reinforcement learning
W Yang, H Yu, B Cui, R Sui, T Gu - Artificial Intelligence Review, 2023 - Springer
It is of great significance to compress neural network models so that they can be deployed
on resource-constrained embedded mobile devices. However, due to the lack of theoretical …
on resource-constrained embedded mobile devices. However, due to the lack of theoretical …